Triple
T1608965
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ten Pound Island Light |
E34571
|
entity |
| Predicate | hasConstructionYear |
P19392
|
FINISHED |
| Object | 1881 |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: 1881 | Statement: [Ten Pound Island Light, hasConstructionYear, 1881]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasConstructionYear Context triple: [Ten Pound Island Light, hasConstructionYear, 1881]
-
A.
yearBuilt
chosen
Indicates the specific year in which something (typically a structure or object) was constructed or completed.
-
B.
constructionDate
Indicates the date on which an entity (such as a building or structure) was constructed or completed.
-
C.
purchaseYear
Indicates the calendar year in which a purchase or acquisition of something took place.
-
D.
accessionYear
Indicates the calendar year in which an item, record, or entity was formally added to or registered within a collection, system, or institution.
-
E.
reconstructionYear
Indicates the year in which something was rebuilt, restored, or reconstructed after damage, alteration, or destruction.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69a885fea6a481909fe83ba6441f1774 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69a93fa6926081908bc78d15c0be3185 |
completed | March 5, 2026, 8:32 a.m. |
| PD | Predicate disambiguation | batch_69a907c35f848190a2428c52e81d013e |
completed | March 5, 2026, 4:34 a.m. |
Created at: March 4, 2026, 7:28 p.m.